Back to search results
Qwen3-4B · IQ4_XS
NVIDIA RTX 408016GBOllama v0.52L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-4B (IQ4_XS) on NVIDIA RTX 4080 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
104.26 tok/s
Decode
Decode speed
504.67 tok/s
Prefill
Prefill speed
1.61 s
TTFT
Time to first token
8.32 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- Ollama · IQ4_XS (current)Decode 104.26 · Prefill 504.67 ·
Core figures
- Decode (avg)
- 104.26 tok/s
- Prefill (avg)
- 504.67 tok/s
- TTFT (avg)
- 1.61 s
- VRAM (avg)
- 8.32 GB
- MTP acceptance rate
- —
- TTFB
- 0.83 GB
- Power draw
- 367.7 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-4B
- Quantization
- IQ4_XS
- Framework
- Ollama
- Version
- v0.52
- Context length
- 16384 tokens
- Batch size
- 512
- GPU layers
- 28
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 4080
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 8.32 GB
- OS
- Windows 11 23H2
- Driver
- 560.94
- CUDA
- 12.4
- Power draw
- 367.7 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.52 · Windows 11 23H2 · CUDA 12.4 · 16384 ctx
104.26 tok/s
Decode
504.67 tok/s
Prefill
1.61 s
TTFT
8.32 GB
VRAM
—
MTP
367.7 W
Power draw
L2 batch seed 2026-10-13: Ollama on hw_id=41 running model_id=54 at IQ4_XS